Tag
This thread explores how the brain's dual memory systems (hippocampus and neocortex) offer lessons for building long-running AI agents, arguing that agents need a fast episodic capture and slow consolidation mechanism to avoid catastrophic interference, rather than relying solely on frozen models with temporary scaffolding.
The article draws an analogy between Tolstoyan art, which transmits feelings without revealing the artist's personal experience, and zero-knowledge proofs, which convince a verifier of a claim without revealing the underlying secret.